Publications related to Byzantine tolerant gradient descent for distributed machine learning with adversaries

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Hristo Georgiev Papazov, Scott William Pesme

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

Wenlong Liao, Zhe Yang

Supervised machine learning models are receiving increasing attention in electricity theft detection due to their high detection accuracy. However, their performance depends on a massive amount of labeled training data, which comes from time-consuming and ...

Piscataway2024

SIMPLE HIERARCHICAL PLANNING WITH DIFFUSION

Caglar Gulcehre, Chang Chen

Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for long- horizon tas ...

2024

Predicting the long-term collective behaviour of fish pairs with deep learning

Francesco Mondada, Alexandre Massoud Alahi, Vaios Papaspyros

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

2024

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Seyed Mohammad Mahdi Johari

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

EPFL2024

Micropreparative Gel Electrophoresis for Purification of Nanoscale Bioconjugates

Ardemis Anoush Boghossian, Yahya Rabbani, Shang-Jung Wu, Vitalijs Zubkovs, Sayyed Hashem Sajjadi

Conventional techniques for purifying macromolecular conjugates often require complex and costly installments that are inaccessible to most laboratories. In this work, we develop a one-step micropreparative method based on a trilayered polyacrylamide gel e ...

2024

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

Amsterdam2024

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Alexandre Massoud Alahi, Mohamed Ossama Ahmed Abdelfattah, Mariam Ahmed Mahmoud Hegazy Hassan

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

2024

Incorporating Projective Geometry into Deep Learning

Michal Jan Tyszkiewicz

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

EPFL2024

Byzantine tolerant gradient descent for distributed machine learning with adversaries

Graph Chatbot

Chat with Graph Search

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Aggregating Spatial and Photometric Context for Photometric Stereo

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

SIMPLE HIERARCHICAL PLANNING WITH DIFFUSION

Predicting the long-term collective behaviour of fish pairs with deep learning

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Micropreparative Gel Electrophoresis for Purification of Nanoscale Bioconjugates

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Incorporating Projective Geometry into Deep Learning

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

Predicting the long-term collective behaviour of fish pairs with deep learning

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Aggregating Spatial and Photometric Context for Photometric Stereo

SIMPLE HIERARCHICAL PLANNING WITH DIFFUSION

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Micropreparative Gel Electrophoresis for Purification of Nanoscale Bioconjugates

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Incorporating Projective Geometry into Deep Learning